{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:45:49Z","timestamp":1743007549263,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319566863"},{"type":"electronic","value":"9783319566870"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-56687-0_10","type":"book-chapter","created":{"date-parts":[[2017,3,27]],"date-time":"2017-03-27T21:54:23Z","timestamp":1490651663000},"page":"113-126","source":"Crossref","is-referenced-by-count":2,"title":["Pose-Selective Max Pooling for Measuring Similarity"],"prefix":"10.1007","author":[{"given":"Xiang","family":"Xiang","sequence":"first","affiliation":[]},{"given":"Trac D.","family":"Tran","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,3,29]]},"reference":[{"key":"10_CR1","unstructured":"Abu-El-Haija, S., Kothari, N., Lee, J., Natsev, P., Toderici, G., Varadarajan, B., Vijayanarasimhan, S.: Youtube-8m: a large-scale video classification benchmark. arXiv: 1609.08675 , September 2016"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Boureau, Y.L., Bach, F., LeCun, Y., Ponce, J.: Learning mid-level features for recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2010)","DOI":"10.1109\/CVPR.2010.5539963"},{"key":"10_CR3","unstructured":"Boureau, Y.L., Ponce, J., LeCun, Y.: A theoretical analysis of feature pooling in visual recognition. In: Proceedings of the International Conference on Machine Learning (2010)"},{"key":"10_CR4","unstructured":"Crosswhite, N., Byrne, J., Parkhi, O.M., Stauffer, C., Cao, Q., Zisserman, A.: Template adaptation for face verification and identification. arxiv, April 2016. https:\/\/arxiv.org\/abs\/1603.03958"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L.A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Fan, W., Yeung, D.-Y.: Face recognition with image sets using hierarchically extracted exemplars from appearance manifolds. In: 7th International Conference on Automatic Face and Gesture Recognition, pp. 177\u2013182. IEEE (2006)","DOI":"10.1109\/FGR.2006.47"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Hadid, A., Pietikainen, M.: Selecting models from videos for appearance-based face recognition. In: Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, vol. 1, pp. 304\u2013308. IEEE (2004)","DOI":"10.1109\/ICPR.2004.1334113"},{"key":"10_CR8","doi-asserted-by":"crossref","first-page":"5967","DOI":"10.1109\/TIP.2015.2493448","volume":"24","author":"Z Huang","year":"2015","unstructured":"Huang, Z., Shan, S., Wang, R., Zhang, H., Lao, S., Kuerban, A., Chen, X.: A benchmark and comparative study of video-based face recognition on COX face database. IEEE Trans. Image Process. 24, 5967\u20135981 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. arXiv:1408.5093 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Kemelmacher-Shlizerman, I., Seitz, S.M., Miller, D., Brossard, E.: The megaface benchmark: 1 million faces for recognition at scale. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.527"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Learned-Miller, E., Huang, G.B., RoyChowdhury, A., Li, H., Hua, G.: Labeled faces in the wild: a survey. Advances in Face Detection and Facial Image Analysis, pp. 189\u2013248 (2016)","DOI":"10.1007\/978-3-319-25958-1_8"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Mian, R.: Unsupervised learning from local features for video-based face recognition. In: 8th IEEE International Conference on Automatic Face & Gesture Recognition, FG 2008, pp. 1\u20136. IEEE (2008)","DOI":"10.1109\/AFGR.2008.4813310"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A.: Deep face recognition. In: British Machine Vision Conference (2015)","DOI":"10.5244\/C.29.41"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Park, U. Jain, A. K., Ross, A.: Face recognition in video: Adaptive fusion of multiple matchers. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383378"},{"key":"10_CR15","unstructured":"Pigou, L., van den Oord, A., Dieleman, S., Herreweghe, M.V., Dambre, J.: Beyond temporal pooling: recurrence and temporal convolutions for gesture recognition in video. arxiv, June 2015. https:\/\/arxiv.org\/abs\/1506.01911"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Stallkamp, J., Ekenel, H.K., Stiefelhagen, R.: Video-based face recognition on real-world data. In: IEEE 11th International Conference on Computer Vision, ICCV 2007, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/ICCV.2007.4408868"},{"key":"10_CR18","unstructured":"Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: Advances in Neural Information Processing Systems (2014)"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE International Conference on Computer Vision (2014)","DOI":"10.1109\/CVPR.2014.220"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Thomas, D., Bowyer, K.W., Flynn, P.J.: Multi-frame approaches to improve face recognition. In: IEEE Workshop on Motion and Video Computing, WMVC 2007, IEEE (2007)","DOI":"10.1109\/WMVC.2007.29"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. In: Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2014)","DOI":"10.3115\/v1\/N15-1173"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Wolf, L., Hassner, T., Maoz, I.: Face recognition in unconstrained videos with matched background similarity. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2011)","DOI":"10.1109\/CVPR.2011.5995566"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Xiang, X., Dao, M., Hager, G.D., Tran, T.D.: Hierarchical sparse and collaborative low-rank representation for emotion recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3811\u20133815. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178684"},{"issue":"6","key":"10_CR24","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1016\/j.imavis.2005.08.004","volume":"24","author":"Y Zhang","year":"2006","unstructured":"Zhang, Y., Martinez, A.M.: A weighted probabilistic ap-proach to face recognition from multiple images and videosequences. Image Vis. Comput. 24(6), 626\u2013638 (2006)","journal-title":"Image Vis. Comput."}],"container-title":["Lecture Notes in Computer Science","Video Analytics. Face and Facial Expression Recognition and Audience Measurement"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-56687-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,20]],"date-time":"2019-09-20T03:16:36Z","timestamp":1568949396000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-56687-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319566863","9783319566870"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-56687-0_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}